We are GoodAI, sister company of Keen Software House who has developed Space Engineers, a successful sandbox game that has sold 5 million copies around the world!

We are an innovative technology company pioneering the development of a system that houses Large Language Model (LLM) driven agents. These intelligent agents continually learn, adapt, and leverage their long-term memory to achieve their goals, providing a seamless and intuitive user experience. Our mission is underpinned by a strong commitment to safety, quality, and reliability. 

We are looking for Software Engineer to contribute to the development of a continual learning system for a Large Language Model (LLM) agent. The selected candidate will become a valuable member of a specialized team that is focused on building an LLM agent capable of both continuous learning and self-improvement through feedback and experience. 

If you are passionate about learning, personal growth, and actively participating in this innovative project, we invite you to apply.  

This project aims to culminate in a production-ready product, so experience with deploying to production environments is essential.

Responsibilities

• Develop a comprehensive continual learning system for agents based on LLMs.

• Create agents that can leverage continual learning to continuously improve themselves in response to requests and feedback from the user and environment.

• Participate in testing and refining systems for minimal latency and optimized streaming output from LLM.

• Contribute to comparative analysis of existing technologies and the decision-making process for adopting or developing solutions.

• Help ensure that the developed solutions are cost-effective and scalable.

• Collaborate with the broader team to integrate these solutions into web and mobile applications. 

• Production Deployment: Take ownership of deploying the continual learning system to production environments, ensuring seamless delivery and minimum downtime.

• Feedback Loop Management: Establish and maintain mechanisms for collecting and integrating user feedback into ongoing system improvements.

• User-Centric Focus: Continually strive to push products out to users, ensuring that the deployed LLM agent meets user expectations and addresses their needs effectively.

• Performance Monitoring: Monitor the health, performance, and overall success metrics of the deployed LLM agent, post-launch.

• Security and Compliance: Ensure that the product meets all necessary security and compliance standards.

We Offer

• Great team!

• Effective development & processes not delayed by bureaucracy

• Work on a product with an ambition for being novel

• Opportunity to make a significant impact

• Healthy work-life balance and five weeks of paid holidays

• Unlimited sick days (we trust our people)

• Unique working environment – Oranzerie

• Remote collaboration is the norm – take home office anytime you want or work from another country

• Relocation package

• Competitive compensation

• Stock options

• Family-friendly

• Team socialization – games, parties, outdoor activities, trips. Bring your family members!

• Talent development and long career rewards – time dedicated for study.

• Company-paid online and offline education courses, books and magazines, participation at industry conferences and workshops

• Studio cafeteria with free coffee and healthy fruit days

• Regular company lunches and outside grills

• Advocate for Rapid Prototyping (try things fast)

• Capable of producing robust, reliable solutions.

• Familiarity with the use of Large Language Models and their operation.

• Experience and understanding of LLM agents

• Proficiency in programming languages such as Python, JavaScript, Java, or C++ or C#

• An action-driven problem solver who thrives on shipping products, not just perfecting them. We need individuals who are eager to put their work out into the world, not just run experiments or follow processes.

• Experience with implementing working-memory and dynamic long-term memory to LLM agents, solving various continual learning use cases, Retrieval-augmented generation (RAG), long context LLMs, fine-tuning retrieval, finetuning agent reasoning and planning and improving instruction following and avoiding hallucinations

• Experience in front-end development technologies and frameworks.

• Team player with a respectful, friendly approach.

• Passion for LLM agents that can continually learn and adapt

Considered plus

• Bachelor’s degree in Computer Science, Software Engineering, or a related field.

• Experience with AI technologies and other Machine Learning frameworks.

• Familiarity with current research into LLMs and LLM agents and their applications. 

• Familiarity with cloud-based solutions and their cost-optimization.